我有一个非常基本的蜘蛛，看起来像是来自沙哑的测试蜘蛛的追随者蜘蛛。
import re
import scrapy.signals
from scrapy.http import Request, HtmlResponse
from scrapy.linkextractors import LinkExtractor
from six.moves.urllib.parse import urlparse
from page import Page
class ZenSpider( scrapy.Spider ) :
def __init__(self) :
super().__init__()
name = 'followall'
custom_settings = {
'CLOSESPIDER_PAGECOUNT' : 2,
"FEEDS" : {
"items.csv" : {"format" : "csv"},
},
}
def __init__(self, **kw) :
super( ZenSpider, self ).__init__( **kw )
url = kw.get( 'url' ) or kw.get( 'domain' ) or 'http://scrapinghub.com/'
if not url.startswith( 'http://' ) and not url.startswith( 'https://' ) :
url = 'http://%s/' % url
self.url = url
self.allowed_domains = [re.sub(r'^www\.', '', urlparse(url).hostname)]
self.link_extractor = LinkExtractor()
def start_requests(self):
return [Request(self.url, callback=self.parse, dont_filter=True)]
def parse(self, response):
"""Parse a PageItem and all requests to follow
@url http://www.scrapinghub.com/
@returns items 1 1
@returns requests 1
@scrapes url title foo
"""
page = self._get_item(response)
r = [page]
r.extend(self._extract_requests(response))
return r
def _get_item(self, response):
items = []
item = Page(
url=response.url,
size=str( len( response.body ) ),
status=response.status,
# content_type=response.request.headers.get('Content-Type'),
# encoding=response.request.headers.get('encoding'),
# referer=response.request.headers.get('Referer'),
)
self._set_title( item, response )
self._set_description( item, response )
return item
def _extract_requests(self, response):
r = []
if isinstance(response, HtmlResponse):
links = self.link_extractor.extract_links( response )
r.extend( Request( x.url, callback=self.parse ) for x in links )
return r
def _set_title(self, page, response) :
if isinstance( response, HtmlResponse ) :
title = response.xpath( "//title/text()" ).extract()
if title :
page['title'] = title[0]
def _set_description(self, page, response) :
if isinstance( response, HtmlResponse ) :
description = response.xpath( "//meta[@name='description']/@content" ).extract()
if description :
page['description'] = description[0]
我正在从以下脚本中调用此蜘蛛。蜘蛛使用CrawlRunner类运行，并且在获取项目时会发出p.signals.connect信号，然后调用方法crawler_results并打印抓取的项目。
据我所知，我无法将爬网移到它自己的类中，因为这样该信号将无法与PyQt5一起使用
import scrapy
from PyQt5 import QtWidgets, QtCore, QtGui
from PyQt5.QtCore import QRunnable, pyqtSlot, QThread, pyqtSignal, QTimer
from PyQt5.QtWidgets import QTableWidgetItem, QLabel
from scrapy import signals
from scrapy.crawler import CrawlerProcess, CrawlerRunner
from twisted.internet import reactor
from scrapy.utils.log import configure_logging
from Layout import Ui_MainWindow
from ZenSpider import ZenSpider
class MainWindow( QtWidgets.QMainWindow, Ui_MainWindow ) :
def __init__(self, parent=None) :
super(MainWindow, self).__init__()
self.setupUi( self )
self.pushButton.pressed.connect( self.on_url_entered )
def crawler_results(self, item) :
print( "SCRAPED AN ITEM" )
##Do Something here ##
def on_url_entered(self) :
# global userInput
# userInput = self.urlbar.text()
configure_logging()
runner = CrawlerRunner()
runner.crawl(ZenSpider, domain="google.com.au")
for p in runner.crawlers :
p.signals.connect(self.crawler_results, signal=signals.item_scraped)
reactor.run()
if __name__ == "__main__" :
app = QtWidgets.QApplication( [] )
main_window = MainWindow()
main_window.show()
app.exec_()
我有一个带有简单QTableWidget和一个按钮的布局
# -*- coding: utf-8 -*-
# Form implementation generated from reading ui file 'basic.ui'
#
# Created by: PyQt5 UI code generator 5.14.2
#
# WARNING! All changes made in this file will be lost!
from PyQt5 import QtCore, QtGui, QtWidgets
class Ui_MainWindow(object):
def setupUi(self, MainWindow):
MainWindow.setObjectName("MainWindow")
MainWindow.resize(1034, 803)
self.centralwidget = QtWidgets.QWidget(MainWindow)
self.centralwidget.setObjectName("centralwidget")
self.tableWidget = QtWidgets.QTableWidget(self.centralwidget)
self.tableWidget.setGeometry(QtCore.QRect(140, 200, 831, 401))
self.tableWidget.setObjectName("tableWidget")
self.tableWidget.setColumnCount(1)
self.tableWidget.setRowCount(0)
item = QtWidgets.QTableWidgetItem()
self.tableWidget.setHorizontalHeaderItem(0, item)
self.pushButton = QtWidgets.QPushButton(self.centralwidget)
self.pushButton.setGeometry(QtCore.QRect(880, 610, 89, 25))
self.pushButton.setObjectName("pushButton")
MainWindow.setCentralWidget(self.centralwidget)
self.statusbar = QtWidgets.QStatusBar(MainWindow)
self.statusbar.setObjectName("statusbar")
MainWindow.setStatusBar(self.statusbar)
self.retranslateUi(MainWindow)
QtCore.QMetaObject.connectSlotsByName(MainWindow)
def retranslateUi(self, MainWindow):
_translate = QtCore.QCoreApplication.translate
MainWindow.setWindowTitle(_translate("MainWindow", "MainWindow"))
item = self.tableWidget.horizontalHeaderItem(0)
item.setText(_translate("MainWindow", "URL"))
self.pushButton.setText(_translate("MainWindow", "Start"))
if __name__ == "__main__":
import sys
app = QtWidgets.QApplication(sys.argv)
MainWindow = QtWidgets.QMainWindow()
ui = Ui_MainWindow()
ui.setupUi(MainWindow)
MainWindow.show()
sys.exit(app.exec_())
[当我按下按钮时，我会看到搜寻器正在运行，并且正在输入crawler_results方法，因为它会打印抓取的项目。蜘蛛程序将每个项目作为以下值返回
{'size': '164125',
'status': 200,
'title': 'Google Advanced Search',
'url': 'https://www.google.com.au/advanced_search?hl=en-AU&authuser=0'}
页面只是我的易碎物品
import scrapy
class Page(scrapy.Item):
url = scrapy.Field()
size = scrapy.Field()
status = scrapy.Field()
title = scrapy.Field()
我的问题是，只要蜘蛛运行，如何将这些数据转换为GUI并自动刷新。这意味着每次刮取一个项目时，GUI都会更新，然后爬网会继续。
我到目前为止已经探索过
非常感谢您的帮助
您必须安装与Qt事件循环兼容的反应堆，例如使用qt5reactor（qt5reactor）：
python -m pip install qt5reactor